{"id":"https://openalex.org/W7212038779","doi":"https://doi.org/10.64898/2026.09.08.750034","title":"Machine learning prediction of eukaryotic hosts for giant viruses","display_name":"Machine learning prediction of eukaryotic hosts for giant viruses","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212038779","doi":"https://doi.org/10.64898/2026.09.08.750034"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.08.750034","doi":"https://doi.org/10.64898/2026.09.08.750034","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750034","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.08.750034.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.08.750034.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106635402","display_name":"Hsin-Ying Chang","orcid":"https://orcid.org/0009-0002-7141-5265","observed_orcids":["https://orcid.org/0009-0002-7141-5265"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210093852","display_name":"Institute of Plant and Microbial Biology, Academia Sinica","ror":"https://ror.org/00jj3h083","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I4210141710","display_name":"Institute of Statistical Science, Academia Sinica","ror":"https://ror.org/044gv5910","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Hsin-Ying Chang","raw_affiliation_strings":["Bioinformatics Program, Institute of Statistical Science, Taiwan International Graduate Program, Academia Sinica, Taipei 11529, Taiwan","Bioinformatics Program, Taiwan International Graduate Program, National Taiwan University, Taipei 10617, Taiwan","DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA 94598, USA","Institute of Plant and Microbial Biology, Academia Sinica, Taipei 11529, Taiwan"],"raw_orcid":"https://orcid.org/0009-0002-7141-5265","affiliations":[{"raw_affiliation_string":"Bioinformatics Program, Institute of Statistical Science, Taiwan International Graduate Program, Academia Sinica, Taipei 11529, Taiwan","institution_ids":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]},{"raw_affiliation_string":"Bioinformatics Program, Taiwan International Graduate Program, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]},{"raw_affiliation_string":"Institute of Plant and Microbial Biology, Academia Sinica, Taipei 11529, Taiwan","institution_ids":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064963970","display_name":"Frederik Schulz","orcid":"https://orcid.org/0000-0002-4932-4677","observed_orcids":["https://orcid.org/0000-0002-4932-4677"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederik Schulz","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA 94598, USA"],"raw_orcid":"https://orcid.org/0000-0002-4932-4677","affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041628541","display_name":"Chuan Ku","orcid":"https://orcid.org/0000-0001-6414-4423","observed_orcids":["https://orcid.org/0000-0001-6414-4423"]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210093852","display_name":"Institute of Plant and Microbial Biology, Academia Sinica","ror":"https://ror.org/00jj3h083","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I4210141710","display_name":"Institute of Statistical Science, Academia Sinica","ror":"https://ror.org/044gv5910","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chuan Ku","raw_affiliation_strings":["Bioinformatics Program, Institute of Statistical Science, Taiwan International Graduate Program, Academia Sinica, Taipei 11529, Taiwan","Bioinformatics Program, Taiwan International Graduate Program, National Taiwan University, Taipei 10617, Taiwan","Institute of Plant and Microbial Biology, Academia Sinica, Taipei 11529, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6414-4423","affiliations":[{"raw_affiliation_string":"Bioinformatics Program, Institute of Statistical Science, Taiwan International Graduate Program, Academia Sinica, Taipei 11529, Taiwan","institution_ids":["https://openalex.org/I4210141710","https://openalex.org/I84653119"]},{"raw_affiliation_string":"Bioinformatics Program, Taiwan International Graduate Program, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Plant and Microbial Biology, Academia Sinica, Taipei 11529, Taiwan","institution_ids":["https://openalex.org/I4210093852","https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041628541"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210093852","https://openalex.org/I4210141710","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.014499999582767487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13220","display_name":"Plant and Fungal Interactions Research","score":0.013399999588727951,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/giant-viruses","display_name":"giant viruses","score":1.0},{"id":"https://openalex.org/keywords/nucleocytoviricota","display_name":"Nucleocytoviricota","score":0.9639999866485596},{"id":"https://openalex.org/keywords/host-prediction","display_name":"host prediction","score":0.7710000276565552},{"id":"https://openalex.org/keywords/eukaryotic-hosts","display_name":"eukaryotic hosts","score":0.8679999709129333},{"id":"https://openalex.org/keywords/metagenome-assembled-genomes","display_name":"metagenome-assembled genomes","score":0.843999981880188},{"id":"https://openalex.org/keywords/gene-content","display_name":"gene content","score":0.6779999732971191},{"id":"https://openalex.org/keywords/sequence-similarity","display_name":"sequence similarity","score":0.7379999756813049},{"id":"https://openalex.org/keywords/virus-host-interactions","display_name":"host-virus interaction","score":0.8790000081062317},{"id":"https://openalex.org/keywords/viral-ecology","display_name":"viral ecology","score":0.4490000009536743},{"id":"https://openalex.org/keywords/host-classification","display_name":"host classification","score":0.3140000104904175}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7943999767303467},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6940000057220459},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6216999888420105},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.5171999931335449},{"id":"https://openalex.org/C2779413310","wikidata":"https://www.wikidata.org/wiki/Q19088","display_name":"Eukaryote","level":4,"score":0.5153999924659729},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5113000273704529},{"id":"https://openalex.org/C124388736","wikidata":"https://www.wikidata.org/wiki/Q3247497","display_name":"Tree of life (biology)","level":4,"score":0.5108000040054321},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.49709999561309814},{"id":"https://openalex.org/C2780317381","wikidata":"https://www.wikidata.org/wiki/Q3754404","display_name":"Giant Virus","level":4,"score":0.4431000053882599},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.36570000648498535},{"id":"https://openalex.org/C2780929364","wikidata":"https://www.wikidata.org/wiki/Q3418768","display_name":"Ranavirus","level":3,"score":0.35589998960494995},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C188880781","wikidata":"https://www.wikidata.org/wiki/Q2430501","display_name":"Three-domain system","level":4,"score":0.32850000262260437},{"id":"https://openalex.org/C8769409","wikidata":"https://www.wikidata.org/wiki/Q2066554","display_name":"Viral evolution","level":4,"score":0.32010000944137573},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C20850961","wikidata":"https://www.wikidata.org/wiki/Q478216","display_name":"Virus classification","level":4,"score":0.30809998512268066},{"id":"https://openalex.org/C3019737400","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host specificity","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.08.750034","doi":"https://doi.org/10.64898/2026.09.08.750034","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750034","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.08.750034.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.08.750034","doi":"https://doi.org/10.64898/2026.09.08.750034","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.08.750034","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.08.750034.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212038779.pdf","grobid_xml":"https://content.openalex.org/works/W7212038779.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2777369046","https://openalex.org/W4293456291","https://openalex.org/W4409958298","https://openalex.org/W4411296705","https://openalex.org/W4411312030","https://openalex.org/W4415795675","https://openalex.org/W7202340383","https://openalex.org/W7204650474"],"related_works":["https://openalex.org/W7204090546","https://openalex.org/W7015215553","https://openalex.org/W4404666904","https://openalex.org/W3109892733","https://openalex.org/W3194221544","https://openalex.org/W7204748466","https://openalex.org/W4382403846","https://openalex.org/W2919326595","https://openalex.org/W4402595532","https://openalex.org/W4366602379"],"abstract_inverted_index":{"ABSTRACT":[0],"Giant":[1],"viruses":[2,131,166],"(GVs;":[3],"Nucleocytoviricota":[4],")":[5],"infect":[6],"diverse":[7],"eukaryotes":[8],"and":[9,69,86,114,132,156,159,189,195,202],"are":[10,31],"ecologically":[11],"important":[12],"across":[13,137,177],"ecosystems.":[14,162],"Although":[15],"cultivation-independent":[16],"sequencing":[17],"has":[18],"recovered":[19],"tens":[20],"of":[21,23,42,93,181,186,205],"thousands":[22],"GV":[24,63,123,139],"genomes":[25,64,125],"from":[26,62,145,169],"environmental":[27,206],"samples,":[28],"eukaryotic":[29,60,179],"hosts":[30,61,88,127,136,176],"only":[32,168],"known":[33,167],"for":[34,199],"a":[35],"few":[36],"isolates,":[37],"leaving":[38],"the":[39,178,197],"host":[40,151],"contexts":[41],"most":[43],"GVs":[44],"elusive.":[45],"We":[46],"developed":[47],"GVHoP":[48,80,119,164],"(":[49],"G":[50],"iant":[51],"V":[52],"irus-":[53],"Ho":[54],"st":[55],"P":[56],"redictor)":[57],"that":[58,141],"predicts":[59,87],"by":[65],"integrating":[66],"gene":[67],"content":[68],"GV-eukaryotic":[70],"sequence":[71],"similarities.":[72],"Trained":[73],"on":[74,193],"isolates":[75],"with":[76],"experimentally":[77],"identified":[78],"hosts,":[79],"achieved":[81],"97%":[82],"accuracy":[83],"in":[84,106],"cross-validation":[85],"at":[89],"three":[90],"hierarchical":[91],"levels":[92],"eukaryote":[94],"classification.":[95],"Functional":[96],"analyses":[97],"link":[98],"top":[99],"predictive":[100],"features":[101],"to":[102,120,128,173],"various":[103],"processes":[104],"involved":[105],"virus-host":[107],"interactions,":[108],"including":[109],"viral":[110],"entry,":[111],"replication,":[112],"morphogenesis,":[113],"cellular":[115],"metabolic":[116],"reprogramming.":[117],"Applying":[118],"7,":[121],"897":[122],"metagenome-assembled":[124],"assigned":[126],"5,":[129],"280":[130],"uncovered":[133],"potential":[134,191],"novel":[135],"major":[138],"orders":[140],"cannot":[142],"be":[143],"inferred":[144],"core-gene":[146],"phylogenetic":[147],"information.":[148],"The":[149],"predicted":[150],"composition":[152],"clearly":[153],"separates":[154],"aquatic":[155,161],"terrestrial":[157],"environments":[158],"distinct":[160],"Together,":[163],"links":[165],"nucleic":[170],"acid":[171],"sequences":[172],"their":[174,190],"putative":[175],"tree":[180],"life,":[182],"improves":[183],"our":[184],"understanding":[185],"GV-host":[187],"interactions":[188],"impacts":[192],"ecosystems,":[194],"paves":[196],"way":[198],"further":[200],"ecological":[201],"functional":[203],"studies":[204],"GVs.":[207]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-10T00:00:00"}
